Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

updating for empty unloads #445

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

updating for empty unloads #445

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/main/scala/com/databricks/spark/redshift/RedshiftJDBCWrapper.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,9 @@ private[redshift] class JDBCWrapper {
fields(i) = StructField(columnName, columnType, nullable)
i = i + 1
}
new StructType(fields)
val schema = new StructType(fields)
log.info("Redshift gave us the following schema: ", schema)
schema
} finally {
ps.close()
}
Expand Down
20 changes: 12 additions & 8 deletions src/main/scala/com/databricks/spark/redshift/RedshiftRelation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,16 +22,15 @@ import java.net.URI
import org.apache.spark.sql.catalyst.encoders.RowEncoder

import scala.collection.JavaConverters._

import com.amazonaws.auth.AWSCredentialsProvider
import com.amazonaws.services.s3.AmazonS3Client
import com.amazonaws.services.s3.model.AmazonS3Exception
import com.eclipsesource.json.Json
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.sources._
import org.apache.spark.sql.types._
import org.apache.spark.sql.{DataFrame, Row, SaveMode, SQLContext}
import org.apache.spark.sql.{DataFrame, Row, SQLContext, SaveMode}
import org.slf4j.LoggerFactory

import com.databricks.spark.redshift.Parameters.MergedParameters

/**
Expand Down Expand Up @@ -145,13 +144,18 @@ private[redshift] case class RedshiftRelation(
Utils.fixS3Url(Utils.removeCredentialsFromURI(URI.create(tempDir)).toString)
val s3URI = Utils.createS3URI(cleanedTempDirUri)
val s3Client = s3ClientFactory(creds)
val is = s3Client.getObject(s3URI.getBucket, s3URI.getKey + "manifest").getObjectContent
val s3Files = try {
val entries = Json.parse(new InputStreamReader(is)).asObject().get("entries").asArray()
entries.iterator().asScala.map(_.asObject().get("url").asString()).toSeq
} finally {
is.close()
val is = s3Client.getObject(s3URI.getBucket, s3URI.getKey + "manifest").getObjectContent
try {
val entries = Json.parse(new InputStreamReader(is)).asObject().get("entries").asArray()
entries.iterator().asScala.map(_.asObject().get("url").asString()).toSeq
} finally {
is.close()
}
} catch {
case _: AmazonS3Exception => Seq()
}

// The filenames in the manifest are of the form s3://bucket/key, without credentials.
// If the S3 credentials were originally specified in the tempdir's URI, then we need to
// reintroduce them here
Expand Down